Uses of Package
com.aparapi

Packages that use com.aparapi

Package	Description
com.aparapi
com.aparapi.device	Contains classes representing OpenCL-capable devices, and "virtual" (java) devices which execute kernels using java.
com.aparapi.internal.kernel
com.aparapi.internal.opencl
com.aparapi.internal.tool
com.aparapi.opencl

Classes in com.aparapi used by com.aparapi

Class and Description
Config.InstructionListener
IProfileReportObserver Defines interface for listener/observer of Kernel profile reports
Kernel A kernel encapsulates a data parallel algorithm that will execute either on a GPU (through conversion to OpenCL) or on a CPU via a Java Thread Pool.
Kernel.EXECUTION_MODE Deprecated. It is no longer recommended that EXECUTION_MODEs are used, as a more sophisticated Device preference mechanism is in place, see KernelManager. Though Kernel.setExecutionMode(EXECUTION_MODE) is still honored, the default EXECUTION_MODE is now Kernel.EXECUTION_MODE.AUTO, which indicates that the KernelManager will determine execution behaviours. The execution mode ENUM enumerates the possible modes of executing a kernel. One can request a mode of execution using the values below, and query a kernel after it first executes to determine how it executed. Aparapi supports 5 execution modes. Default is GPU. Enum value Execution GPU Execute using OpenCL on first available GPU device ACC Execute using OpenCL on first available Accelerator device CPU Execute using OpenCL on first available CPU device JTP Execute using a Java Thread Pool (one thread spawned per available core) SEQ Execute using a single loop. This is useful for debugging but will be less performant than the other modes To request that a kernel is executed in a specific mode, call Kernel.setExecutionMode(EXECUTION_MODE) before the kernel first executes. int[] values = new int[1024]; // fill values array SquareKernel kernel = new SquareKernel(values); kernel.setExecutionMode(Kernel.EXECUTION_MODE.JTP); kernel.execute(values.length); Alternatively, the property com.codegen.executionMode can be set to one of JTP,GPU,ACC,CPU,SEQ when an application is launched. java -classpath ....;codegen.jar -Dcom.codegen.executionMode=GPU MyApplication Generally setting the execution mode is not recommended (it is best to let Aparapi decide automatically) but the option provides a way to compare a kernel's performance under multiple execution modes.
Kernel.KernelState This class is for internal Kernel state management
ProfileInfo
ProfileReport
Range A representation of 1, 2 or 3 dimensional range of execution.

Classes in com.aparapi used by com.aparapi.device

Class and Description
Range A representation of 1, 2 or 3 dimensional range of execution.

Classes in com.aparapi used by com.aparapi.internal.kernel

Class and Description
IProfileReportObserver Defines interface for listener/observer of Kernel profile reports
Kernel A kernel encapsulates a data parallel algorithm that will execute either on a GPU (through conversion to OpenCL) or on a CPU via a Java Thread Pool.
ProfileInfo
ProfileReport
Range A representation of 1, 2 or 3 dimensional range of execution.

Classes in com.aparapi used by com.aparapi.internal.opencl

Class and Description
ProfileInfo

Classes in com.aparapi used by com.aparapi.internal.tool

Class and Description
Config.InstructionListener

Classes in com.aparapi used by com.aparapi.opencl

Class and Description
ProfileInfo